Method and system for automatic positioning of radio frequency coils in cardiac magnetic resonance examinations

Abstract

The application relates to the technical field of medical imaging, and discloses a method and system for automatically positioning a radio frequency coil in a cardiac magnetic resonance examination, which comprises the following steps: acquiring a current cardiac pose of a heart and a current coil pose of the radio frequency coil in a magnetic resonance examination process of the heart; determining a current population based on the current cardiac pose and the current coil pose, wherein the current population comprises a set of parameters for adjusting the position and / or attitude of the radio frequency coil; determining a control instruction based on the current population and the current coil pose by improving a particle swarm algorithm; and positioning the radio frequency coil based on the control instruction to adjust the relative position relationship between the radio frequency coil and the heart. The scheme can improve the accuracy and stability of positioning the radio frequency coil.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, and to, but is not limited to, an automatic positioning method and system for radiofrequency coils in cardiac magnetic resonance imaging. Background Technology

[0002] In cardiac magnetic resonance imaging (MRI) examinations, the relative positional relationship between the radiofrequency coil and the heart directly affects the signal reception strength, image signal-to-noise ratio, and diagnostic reliability of the MRI equipment. Therefore, accurate spatial positioning of the radiofrequency coil is a key prerequisite for obtaining high-quality MRI images.

[0003] In current clinical practice, cardiac MRI scans typically rely on the experience of medical professionals and manual manipulation to adjust the pose and positioning of the radiofrequency coil. Multiple low-resolution verification scans are used to iteratively adjust the coil's position and orientation, gradually refining the relative position between the coil and the heart. However, the positioning accuracy of this approach is limited by the experience level of the medical professionals, resulting in insufficient precision and stability. Summary of the Invention

[0004] Based on the above technical problems, this application provides an automatic positioning method and system for radio frequency coils in cardiac magnetic resonance imaging (MRI) examinations, which can improve the accuracy and stability of radio frequency coil positioning, thereby improving the accuracy and stability of cardiac MRI examinations.

[0005] The technical solution provided in this application is as follows: This application provides an automatic positioning method for radiofrequency coils in cardiac magnetic resonance imaging (MRI) examinations, including: During an MRI scan of the heart, the current heart pose and the current coil pose of the radio frequency coil are acquired. Based on the current heart pose and the current coil pose, a current population is determined; wherein, the current population includes a set of parameters that are adjusted for the position and / or orientation of the radio frequency coil; the current population is associated with an improved particle swarm optimization algorithm; The control command is determined by improving the particle swarm optimization algorithm based on the current population and the current coil pose. The radio frequency coil is positioned based on the control command to adjust the relative position between the radio frequency coil and the heart.

[0006] This application also provides an automatic positioning system for radiofrequency coils in cardiac magnetic resonance imaging, including: The acquisition module is used to acquire the current heart pose and the current coil pose of the radio frequency coil during a magnetic resonance imaging examination of the heart. A determination module is used to determine the current population based on the current heart pose and the current coil pose; and to determine control commands based on the current population and the current coil pose using an improved particle swarm optimization algorithm; wherein the current population includes a set of parameters for adjusting the position and / or orientation of the radio frequency coil; and the current population is associated with the improved particle swarm optimization algorithm. A positioning module is used to position the radio frequency coil based on the control command, so as to adjust the relative positional relationship between the radio frequency coil and the heart.

[0007] The automatic positioning method for radiofrequency coils in cardiac magnetic resonance imaging provided in this application has at least the following beneficial effects: The automatic positioning method for radio frequency (RF) coils in cardiac magnetic resonance imaging (MRI) provided in this application acquires the current cardiac pose and the current RF coil pose during the MRI examination, achieving tracking acquisition of the current cardiac pose and the current coil pose. Furthermore, based on the current cardiac pose and the current coil pose, a current population associated with an improved particle swarm optimization algorithm is determined. This current population includes a set of parameters that adjust the position and / or orientation of the RF coil. This improves the correlation between the current population and the current cardiac pose and the current coil pose, reducing the probability of parameters in the current population deviating from the spatial range represented by the current cardiac pose and the current coil pose, thereby improving the accuracy of the current population. Based on this, by improving the particle swarm optimization algorithm, control commands are determined based on the current population and the current coil pose. Then, the RF coil is positioned based on the control commands to adjust the relative positional relationship between the RF coil and the heart. This improves the automation and intelligence level of RF coil positioning, increases the efficiency of RF coil positioning, and enhances the accuracy and stability of RF coil positioning, thereby improving the accuracy and stability of cardiac MRI examinations. Attached Figure Description

[0008] Figure 1 A flowchart illustrating the automatic positioning method of the radiofrequency coil in cardiac magnetic resonance imaging provided in this application embodiment; Figure 2 This is a schematic diagram of the automatic positioning system for the radio frequency coil in cardiac magnetic resonance imaging provided in this application embodiment. Detailed Implementation

[0009] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0010] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0011] In cardiac magnetic resonance imaging (MRI) examinations, the relative positional relationship between the radiofrequency coil and the target area of ​​the heart directly affects the signal reception strength, image signal-to-noise ratio, and diagnostic reliability of the MRI equipment. Therefore, accurate spatial positioning of the radiofrequency coil is a key prerequisite for obtaining high-quality MRI images.

[0012] In current clinical practice, the adjustment of the radiofrequency coil's pose and positioning during cardiac MRI examinations is highly dependent on the experience and manual operation of medical staff. This requires medical staff to first visually assess the heart's location using a rough cardiac positioning image, then manually adjust the scanning bed and rotate the radiofrequency coil, and then iteratively adjust the position and / or orientation of the radiofrequency coil through multiple low-resolution verification scans until the relative positional relationship between the radiofrequency coil and the heart meets the requirements of MRI examination.

[0013] Clearly, the above solutions are inefficient, the manual trial-and-error process for medical staff is cumbersome, and it prolongs the overall examination time; moreover, the positioning accuracy of the above solutions is limited by the experience level of medical staff, so their accuracy and stability are insufficient.

[0014] To address these technical challenges, related technologies have offered automated adjustment schemes for magnetic resonance imaging (MRI) equipment. However, these schemes rely on pre-set fixed rules or rudimentary automation based on simple geometric calculations, and are largely unsuitable for cardiac MRI examinations.

[0015] Based on the above technical problems, this application provides an automatic positioning method and system for radio frequency coils in cardiac magnetic resonance imaging. Figure 1 This is a flowchart illustrating the automatic positioning method for radiofrequency coils in cardiac magnetic resonance imaging provided in this application embodiment. Figure 1 As shown, the method may include the following steps: Step 101: During the magnetic resonance imaging (MRI) examination of the heart, acquire the current heart pose and the current coil pose of the radiofrequency coil.

[0016] In some embodiments, after detecting that the target to be detected is lying flat on the scanning table in a specified posture, the magnetic resonance device can switch to magnetic resonance detection state. At this time, the current heart posture and the current coil posture can be acquired. The target to be detected may include a person or other animal.

[0017] In some embodiments, the current heart pose may include the current position of the heart of the target being detected and its orientation, etc.; for example, the current heart pose can be obtained through the following steps: First, the magnetic resonance imaging (MRI) device is controlled to enable ECG gating and respiratory gating, and at least one rapid tri-plane localization scan is performed to capture a relatively stationary image of the heart at end-diastole, and the relatively stationary image is used as the reference image.

[0018] Secondly, preprocessing operations can be performed on the reference image to optimize the heart contour and eliminate artifacts, resulting in a preprocessed image.

[0019] Next, based on the preprocessing results, a hybrid segmentation method combining region growing and active contour modeling is adopted. First, seed points are automatically selected based on cardiac anatomy priors for region growing to obtain an initial cardiac region mask. Then, the boundary of the initial cardiac region mask is used as the initial curve of the active contour model, which iteratively evolves under the drive of the image gradient field, eventually converging to the precise boundary of the cardiac tissue, thus obtaining the three-dimensional point set of the cardiac region. Where N is an integer greater than 2. Used to represent the nth 3D point in a 3D point set, where n is an integer greater than or equal to 1 and less than or equal to N. The active contour model can include the Snake model.

[0020] Finally, based on this point set, the core baseline parameters are calculated, and the geometric center of the heart region is obtained by calculating the mean of the three-dimensional point set. Principal Component Analysis (PCA) was performed on the three-dimensional point set to extract its three principal directions, and a rotation matrix representing the spatial orientation of the heart was constructed based on the three principal directions. By integrating the three-dimensional point set, geometric center, and rotation matrix, a complete spatial mathematical model of the heart can be obtained. .

[0021] For example, preprocessing operations may include using Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance tissue contrast, applying a mid-range filter to suppress noise, and performing morphological opening and closing operations to optimize the cardiac contour and eliminate minor artifacts.

[0022] For example, This represents the nth 3D point in the 3D point set in the image coordinate system. The coordinates below.

[0023] It should be noted that the three main directions mentioned above may include the first main direction, the second main direction, and the third main direction.

[0024] Specifically, the first principal direction is the direction with the largest variance of the three-dimensional point set, which is used to define the most important spatial extension direction of the heart; the second principal direction is the direction with the second largest variance of the three-dimensional point set among all directions orthogonal to the first principal direction, which is used to characterize one of the minor axis directions of the heart. The second principal direction, combined with the first principal direction, defines a major plane of the heart in space; the third principal direction is the direction orthogonal to both the first and second principal directions, which corresponds to the direction with the smallest variance of the data points in the three-dimensional point set, reflecting the thickness or flatness of the heart in this direction. The role of the third principal direction is to form a complete right-handed orthogonal coordinate system describing the spatial orientation of the heart together with the first two principal directions.

[0025] It should be noted that the rotation matrix here... It describes the rotational orientation of the heart's own local coordinate system, defined by PCA, relative to the image coordinate system. The rotation matrix can be formed by arranging the three principal direction vectors analyzed by PCA in columns, describing the orientation of the heart's own coordinate system relative to the image coordinate system.

[0026] In some embodiments, the current coil pose may include the current position and orientation of the RF coil; for example, the current coil pose may be directly measured by a precision position sensing module integrated inside the RF coil, wherein the position sensing module may include an optical encoder or an electromagnetic sensor.

[0027] Specifically, the current coil pose can be determined using the equipment coordinate system where the magnetic resonance device is located. The current coil pose can be defined as the reference point, and may include the three-dimensional spatial coordinates of the RF coil in the device coordinate system. and the attitude matrix used to characterize the RF coil. ,in, The variables in the table are used to characterize the direction vectors of the RF coil relative to the x-axis, y-axis, and z-axis of the device coordinate system.

[0028] Step 102: Determine the current population based on the current heart pose and the current coil pose.

[0029] The current population includes a set of parameters that adjust the position and / or orientation of the RF coils; the current population is associated with the improved particle swarm optimization algorithm.

[0030] In some embodiments, the current population may include a set of multiple parameters that may be used to adjust the position and / or orientation of the RF coil under the current heart pose and current coil pose conditions.

[0031] In some embodiments, the current population can be determined in the following ways: The limit adjustment range of the scanning bed of the magnetic resonance imaging device and the limit adjustment range of the radio frequency coil are obtained. Then, the current population is randomly generated with the limit adjustment range of the bed and the limit adjustment range of the coil as boundary conditions and the current heart pose and the current coil pose as initial conditions.

[0032] For example, the bed limit adjustment range may include the limit range of movement of the scanning bed, while the coil limit adjustment range may include the limit range of adjustment of the position and orientation of the coil; both the bed limit adjustment range and the coil limit adjustment range may vary depending on the magnetic resonance equipment; for example, since the bed limit adjustment range defines the range of movement of the object to be detected, the bed limit adjustment range may constitute the boundary condition of the coil limit adjustment range.

[0033] Step 103: Determine the control command based on the current population and the current coil pose by improving the particle swarm algorithm.

[0034] In some embodiments, the control commands may include commands to adjust the position and / or orientation of the radio frequency coil, and may also include commands to adjust the position of the scanning bed.

[0035] In some embodiments, control commands can be determined in the following ways: By improving the particle swarm optimization algorithm, parameters in the current population are selected to obtain parameters to be evaluated. Then, the pose adjustment result of the current coil pose is predicted based on the parameters to be evaluated. Finally, control commands are generated according to the degree of matching between the pose adjustment result and the current heart pose. For example, if the degree of matching is greater than or equal to the matching threshold, the parameters to be evaluated associated with the degree of matching can be determined as the control parameters of the control command. If the degree of matching is less than the degree threshold, the preceding operations are iteratively executed until the degree of matching is greater than or equal to the matching threshold.

[0036] Step 104: Position the radio frequency coil based on control commands to adjust the relative position between the radio frequency coil and the heart.

[0037] In some embodiments, positioning the radio frequency coil based on control commands may include at least one of the following: Based on the control parameters contained in the control command, the position and / or orientation of the radio frequency coil are gradually adjusted so that the orientation of the radio frequency coil can match the current orientation of the heart, thereby achieving adjustment of the relative positional relationship.

[0038] The position of the scanning bed is adjusted based on the displacement parameters of the scanning bed in the control command, and the position and / or attitude of the radio frequency coil is adjusted based on the adjustment parameters of the position and / or attitude of the radio frequency coil in the control command, so as to achieve the adjustment of the relative position relationship.

[0039] As can be seen from the above, the automatic positioning method for radio frequency coils in cardiac magnetic resonance imaging (MRI) provided in this application acquires the current cardiac pose and the current coil pose during the MRI examination of the heart, achieving tracking acquisition of the current cardiac pose and the current coil pose. Furthermore, based on the current cardiac pose and the current coil pose, a current population is determined, which includes a set of parameters that adjust the position and / or orientation of the radio frequency coil. This improves the correlation between the current population and the current cardiac pose and the current coil pose, reducing the probability of parameters in the current population deviating from the spatial range represented by the current cardiac pose and the current coil pose, thereby improving the accuracy of the current population. Based on this, by improving the particle swarm optimization algorithm, control commands are determined based on the current population and the current coil pose, and then the radio frequency coil is positioned based on the control commands to adjust the relative positional relationship between the radio frequency coil and the heart. This improves the automation and intelligence level of radio frequency coil positioning, increases the efficiency of radio frequency coil positioning, and also improves the accuracy and stability of radio frequency coil positioning, thereby improving the accuracy and stability of cardiac MRI examination.

[0040] Based on the foregoing embodiments, the automatic positioning method for radiofrequency coils in cardiac magnetic resonance imaging provided in this application, which determines control commands based on the current population and the current coil pose using an improved particle swarm optimization algorithm, can be implemented through the following steps: Step A1: Update and improve the inertia weights of the particle swarm algorithm.

[0041] In some embodiments, inertia weights can be used to control the selection rate of parameters in the current population; for example, inertia weights can be updated in the following manner: The inertia weight is updated according to the iteration period of the parameters in the current population. For example, if the iteration period is in the early stage of iteration, the inertia weight can be increased to achieve a global search of the parameters in the current population, while if the iteration period is in the later stage of iteration, the inertia weight can be decreased to achieve a local search of the parameters in the current population.

[0042] Step A2: Based on the updated inertia weights, select parameters in the current population to obtain the parameters to be evaluated.

[0043] In some embodiments, the range of parameter selection can be controlled based on the updated inertia weights, and parameters in the current population can be selected according to the range of parameter selection to obtain the parameters to be evaluated; for example, the range of parameter selection may include the global range corresponding to the global search or the local range corresponding to the local search; wherein, the local range may be a proper subset of the global range.

[0044] Step A3: Predict the predicted coil pose of the RF coil based on the parameters to be evaluated.

[0045] In some embodiments, the predicted coil pose can be obtained in the following way: Based on the position adjustment parameters and attitude adjustment parameters included in the parameters to be evaluated, the position dimension and attitude dimension of the current coil pose are calculated to obtain the predicted coil pose.

[0046] It should be noted that obtaining the predicted coil pose does not involve actual adjustment of the RF coil pose.

[0047] Step A4: Determine the deviation score between the predicted coil pose and the current heart pose; determine the control command based on the deviation score.

[0048] In some embodiments, the deviation score can characterize the magnitude of the position deviation and the attitude deviation; for example, the position deviation may include the deviation between the coil position represented by the predicted coil pose and the heart position represented by the current heart pose, and the attitude deviation may include the deviation between the coil attitude represented by the predicted coil pose and the heart attitude represented by the current heart pose.

[0049] Accordingly, the deviation score can be determined in the following way: The positional and attitude deviations were statistically analyzed to obtain deviation scores.

[0050] In some embodiments, control commands can be determined in the following ways: The control command is determined based on the magnitude of the deviation score; for example, if the deviation score is a first score, the control command includes: adjusting the position and / or orientation of the RF coil in a first direction and a first step; if the deviation score is a second score, the control command includes: adjusting the position and / or orientation of the RF coil in a second direction and a second step.

[0051] The first and second directions may include directions that bring the radio frequency coil closer to the heart. Furthermore, if the first score is greater than the second score, the first step may be greater than the second step. In other words, the step included in the control command may be positively correlated with the deviation score.

[0052] As can be seen from the above, the automatic positioning method for radiofrequency coils in cardiac magnetic resonance imaging provided in this application, after updating and improving the inertial weights of the particle swarm optimization algorithm, selects parameters in the current population based on the updated weights to obtain the parameters to be evaluated. In this way, flexible control of the parameter selection process in the current population can be achieved. On this basis, after predicting the predicted coil pose of the radiofrequency coil based on the parameters to be evaluated, the deviation score between the predicted coil pose and the current cardiac pose is determined, realizing the tracking determination of the predicted coil pose and the deviation score. On the other hand, the control command is determined based on the deviation score, which improves the pertinence of the control command.

[0053] Based on the foregoing embodiments, the automatic positioning method for radiofrequency coils in cardiac magnetic resonance imaging provided in this application, which determines the deviation score between the predicted coil pose and the current cardiac pose, can be achieved through the following steps: Step B1: Determine the motion weight based on the motion deviation threshold and motion correction factor associated with the magnetic resonance examination.

[0054] In some embodiments, the movement deviation threshold may include the maximum value of the movement deviation of the radio frequency coil during the magnetic resonance examination.

[0055] In some embodiments, the motion correction factor can be used to compensate for errors caused by the movement of the RF coil; for example, the motion correction factor can compensate for the movement deviation generated during the movement of the RF coil.

[0056] In some embodiments, the movement weight can be determined in the following ways: The moving weight is obtained by weighting the quotient of the moving correction factor and the moving deviation threshold; specifically, the moving weight can be calculated using the following formula: (1) in, For moving weights, For the moving correction factor, The moving deviation threshold, This is a standardized constant used to weight the quotient of the moving correction factor and the moving deviation threshold.

[0057] Step B2: Determine the rotation weight based on the rotation deviation threshold and rotation correction factor associated with the magnetic resonance examination.

[0058] In some embodiments, the rotation deviation threshold may include the maximum value of the deviation generated when the RF coil is rotated.

[0059] In some embodiments, the rotation correction factor can compensate for deviations caused by the rotation of the RF coil attitude.

[0060] In some embodiments, rotation weights can be determined in the following ways: The quotient of the rotation correction factor and the rotation deviation threshold is weighted based on the standardization constant to obtain the weighted result. Then, the weighted result is corrected based on the rotation importance factor to obtain the rotation weight, as shown in Equation (2): (2) in, For rotation weights, As the rotation importance factor, This is the rotational deviation threshold. This is the rotation correction factor.

[0061] Step B3: Based on the translation weight and rotation weight, process the position deviation and attitude deviation to obtain the deviation score.

[0062] Among them, position deviation includes the deviation between the predicted position in the prediction coil pose and the heart position in the current heart pose; attitude deviation includes the deviation between the predicted pose in the prediction coil pose and the heart pose in the current heart pose.

[0063] In some embodiments, the transformation matrix between the image coordinate system and the device coordinate system can be predetermined. Then, based on the transformation matrix, the current heart pose is transferred to the device coordinate system to obtain the current heart pose in the device coordinate system; for example, Used to characterize the rotation matrix between the image coordinate system and the device coordinate system. This is the translation vector between the image coordinate system and the device coordinate system.

[0064] For example, the current heart pose in the device coordinate system may include the heart position and the heart orientation in the device coordinate system, which can be calculated using the following formula: (3) in, This represents the location of the heart in the device's coordinate system. This represents the heart's orientation in the device coordinate system.

[0065] In some embodiments, the position deviation and attitude deviation can be calculated using the following formula: (4) in, For positional deviation, For attitude deviation, To predict the predicted position in the coil pose, This is the predicted attitude in the predicted coil pose.

[0066] For example, attitude deviation can be expressed using Euler angles as: The various angles in the Euler angles are used to characterize the azimuth angles of the predicted RF coil orientation relative to the x-axis, y-axis, and z-axis of the device coordinate system, respectively.

[0067] For example, the predicted pose and predicted orientation can be calculated using the following formula: (5) in, Indicates the parameter to be evaluated The included displacement parameters, Indicates the parameter to be evaluated The included rotation angle, where j is an integer greater than or equal to 1.

[0068] In some embodiments, the deviation score can be calculated in the following manner: Based on the translation weight and rotation weight, the position deviation and attitude deviation are weighted to obtain the deviation score; specifically as shown in equation (6): (6) in, To compare with the parameters to be evaluated The corresponding deviation score.

[0069] As can be seen from the above, the automatic positioning method for radiofrequency coils in cardiac magnetic resonance imaging (MRI) provided in this application determines the movement weight based on the movement deviation threshold and translation correction factor associated with the MRI examination, and determines the rotation weight based on the rotation offset threshold and rotation correction factor associated with the MRI examination. In this way, the correlation between the movement weight and rotation weight and the corresponding offset threshold and correction factor associated with the MRI examination is improved, thereby improving the accuracy of the rotation weight and movement weight. On this basis, the position deviation and attitude deviation are processed based on the movement weight and rotation weight to obtain the deviation score, which improves the accuracy of the deviation score and also realizes an intuitive and concise representation of the position deviation and attitude deviation.

[0070] Based on the foregoing embodiments, the automatic positioning method for radiofrequency coils in cardiac magnetic resonance imaging provided in this application can be updated and improved by the inertial weights of the particle swarm optimization algorithm in the following ways: Determine the average distance between parameters in the current population; based on the average distance, minimum distance threshold, and maximum distance threshold, update and improve the inertia weights of the particle swarm optimization algorithm.

[0071] In some embodiments, the average distance can characterize the diversity of parameters in the current population; for example, the average distance can be calculated as follows: After the current population is determined, the average distance is obtained by statistically averaging the distances between parameters in the current population.

[0072] In some embodiments, the minimum distance threshold and the maximum distance threshold can be preset or adjusted; wherein, the minimum distance threshold can be used to determine whether the concentration of parameters in the current population is greater than or equal to a first threshold, and the maximum distance threshold can be used to determine whether the dispersion of parameters in the current population is greater than or equal to a second threshold.

[0073] In some embodiments, the inertia weights can be updated using the following formula: (6) in, For the updated inertia weights, The inertia weight is the value after the last update, where k is an integer greater than or equal to 2. The average distance, The maximum distance threshold, The minimum distance threshold, The base adjustment coefficient, which can take a value of 0.95, is used to adjust the update gradient of the inertia weight. This is the amplitude adjustment coefficient, which can take a value of 0.1 and is used to control the range of change of the inertia weight.

[0074] For example, during the initial update of the inertia weights, It can be used to improve the initial inertia weights of the particle swarm algorithm.

[0075] As can be seen from the above, in the automatic positioning method of radio frequency coil in cardiac magnetic resonance examination provided in the embodiments of this application, after determining the average distance between parameters in the current population, the inertial weight of the improved particle swarm algorithm is updated based on the average distance, the minimum distance threshold, and the maximum distance threshold. In this way, the dynamic, flexible and targeted updating of the inertial weight of the improved particle swarm algorithm is realized.

[0076] Based on the foregoing embodiments, the automatic positioning method for radiofrequency coils in cardiac magnetic resonance imaging provided in this application, which determines control commands based on deviation scores, can be implemented in the following ways: If the deviation score is greater than or equal to the score threshold, the adjustment parameter corresponding to the deviation score in the current population will be determined as the control parameter in the control command.

[0077] Accordingly, the above method can also perform the following operations: If the deviation score in the score set is less than the score threshold, the target parameter is updated based on the score set to obtain the next swarm set; by improving the particle swarm algorithm, iterative optimization processing is performed on the current coil based on the next swarm set to obtain the control command.

[0078] The target parameters include the set of parameters in the current population whose deviation scores are less than the score threshold; the score set includes the set of deviation scores corresponding to the parameters in the current population.

[0079] In some embodiments, when all deviation scores in the score set are greater than or equal to the score threshold, the parameter corresponding to the score set with the largest value in the score set can be determined as the control parameter.

[0080] In some embodiments, the control parameters may include a set of parameters for adjusting the displacement and / or attitude of the RF coil, and may also include a set of parameters for adjusting the displacement direction and displacement amount of the scanning bed; for example, the control parameters may include movement parameters for translating the RF coil along the coordinate axes of the device coordinate system, and may also include angle vectors for adjusting the attitude of the RF coil along the coordinate axes of the device coordinate system.

[0081] In some embodiments, if the deviation score is less than the score threshold, a new number of parameters corresponding to the target parameter can be regenerated, and the new parameters can be merged with the candidate parameters in the current population to obtain the next population parameter; for example, the candidate parameters may include a set of parameters in the current population other than the target parameter.

[0082] In some embodiments, after determining the next group parameters, the inertial weights can be updated using the method provided in the foregoing embodiments, and new parameters to be evaluated can be selected from the next group parameters based on the updated inertial weights. Then, a new prediction coil pose can be predicted based on the new parameters to be evaluated. Next, a new position deviation and a new attitude deviation can be determined, and then a new deviation score can be determined. This process is repeated until the deviation score in the score set is greater than or equal to the score threshold. At this point, the parameter corresponding to the deviation score with the largest value can be determined as the control parameter in the control command.

[0083] Table 1 is a summary of data comparisons for four technical solutions for automatically adjusting RF coils.

[0084] Table 1 The first scheme involves medical personnel manually adjusting the position of the radio frequency coil; the second scheme is an automatic position adjustment scheme based on predetermined rules; and the third scheme achieves position adjustment of the radio frequency coil through traditional PSO optimization.

[0085] As can be seen from Table 1, compared with the first to the third schemes, this scheme has significant improvements in positioning time, translation accuracy, rotation accuracy, and positioning success rate.

[0086] As can be seen from the above, the automatic positioning method for radiofrequency coils in cardiac magnetic resonance imaging provided in this application, if the deviation score is greater than or equal to the score threshold, determines the adjustment parameter corresponding to the deviation score in the current population as the control parameter in the control command. This enhances the correlation between the control parameter and the deviation score, thereby improving the pertinence of the control parameter. Furthermore, if the deviation score in the score set is less than the score threshold, the target parameter is updated to obtain the next population set. Based on the next population set, the improved particle swarm optimization algorithm is used to perform iterative optimization processing on the current coil pose to obtain the control command. In this way, the automatic updating of the population set is realized, and the automated iterative optimization processing of the dynamic closed loop of the current coil pose is also realized, thereby improving the automation and intelligence level of the control command determination process.

[0087] Based on the foregoing embodiments, this application also provides an automatic positioning system for radio frequency coils in cardiac magnetic resonance imaging. Figure 2 This is a schematic diagram of the automatic positioning system for the radiofrequency coil in cardiac magnetic resonance imaging provided in this application embodiment, as shown below. Figure 2 As shown, the automatic positioning system 200 may include: The acquisition module 201 is used to acquire the current heart pose and the current coil pose of the radio frequency coil during a magnetic resonance imaging examination of the heart. The determination module 202 is used to determine the current population based on the current heart pose and the current coil pose; and to determine the control command based on the current population and the current coil pose using an improved particle swarm optimization algorithm; wherein, the current population includes a set of parameters for adjusting the position and / or orientation of the radio frequency coil; and the current population is associated with the improved particle swarm optimization algorithm. The positioning module 203 is used to position the radio frequency coil based on control commands in order to adjust the relative positional relationship between the radio frequency coil and the heart.

[0088] In some embodiments, the determining module is used to update the inertia weights of the improved particle swarm optimization algorithm; select parameters in the current population based on the updated inertia weights to obtain parameters to be evaluated; predict the predicted coil pose of the radio frequency coil based on the parameters to be evaluated; determine the deviation score between the predicted coil pose and the current heart pose; and determine control commands based on the deviation score.

[0089] In some embodiments, the determining module is configured to determine a motion weight based on a motion deviation threshold and a translation correction factor associated with the magnetic resonance imaging (MRI) examination; determine a rotation weight based on a rotation deviation threshold and a rotation correction factor associated with the MRI examination; and process the position deviation and attitude deviation based on the motion weight and the rotation weight to obtain a deviation score; wherein the position deviation includes the deviation between the predicted position in the prediction coil pose and the heart position in the current heart pose; and the attitude deviation includes the deviation between the predicted attitude in the prediction coil pose and the heart attitude in the current heart pose.

[0090] In some embodiments, the determining module is used to determine the average distance between parameters in the current population; and to update the inertia weights of the improved particle swarm optimization algorithm based on the average distance, the minimum distance threshold, and the maximum distance threshold.

[0091] In some embodiments, the determining module is used to determine the adjustment parameter corresponding to the deviation score in the current population as the control parameter in the control command if the deviation score is greater than or equal to the score threshold. The determination module is used to update the target parameters based on the score set if the deviation score in the score set is less than the score threshold, and obtain the next population set; wherein, the target parameters include the set of parameters in the current population whose deviation scores are less than the score threshold; the score set includes the set of deviation scores corresponding to the parameters in the current population; The determination module is used to perform iterative optimization processing on the current coil pose based on the next swarm set by improving the particle swarm algorithm, so as to obtain control commands.

[0092] This application also provides the following ablation tests: First ablation test: Remove the step of updating the inertia weights. In this case, a fixed inertia weight can be used to select parameters in the current population; for example, with a fixed inertia weight of 0.9, the translation accuracy decreases by 25%.

[0093] Second ablation test: Removing update operations on the current population reduces the success rate of RF coil localization to 80%.

[0094] The third ablation test: a fixed geometric distance was used instead of the deviation score calculation method in this application, which resulted in a 38% decrease in rotational accuracy.

[0095] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0096] The methods disclosed in the various method embodiments provided in this application can be arbitrarily combined to obtain new method embodiments without conflict.

[0097] The features disclosed in the various product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0098] The features disclosed in the various method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0099] It should be noted that the aforementioned computer-readable storage media can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM), etc.; or it can be various electronic devices including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0100] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0101] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0102] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware nodes. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0103] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0104] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0105] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0106] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An automatic positioning method for a radiofrequency coil in cardiac magnetic resonance imaging (MRI), characterized in that, include: During an MRI scan of the heart, the current heart pose and the current coil pose of the radio frequency coil are acquired. Based on the current heart pose and the current coil pose, a current population is determined; wherein, the current population includes a set of parameters that are adjusted for the position and / or orientation of the radio frequency coil; the current population is associated with an improved particle swarm optimization algorithm; The improved particle swarm optimization algorithm determines the control command based on the current population and the current coil pose. The radio frequency coil is positioned based on the control command to adjust the relative position between the radio frequency coil and the heart.

2. The method according to claim 1, characterized in that, The step of determining control commands based on the current population and the current coil pose using the improved particle swarm optimization algorithm includes: Update the inertia weights of the improved particle swarm optimization algorithm; Based on the updated inertia weights, parameters in the current population are selected to obtain the parameters to be evaluated; The predicted coil pose of the RF coil is predicted based on the parameters to be evaluated; Determine the deviation score between the predicted coil pose and the current heart pose; The control command is determined based on the deviation score.

3. The method according to claim 2, characterized in that, Determining the deviation score between the predicted coil pose and the current heart pose includes: Based on the motion deviation threshold and translation correction factor associated with the magnetic resonance examination, the motion weight is determined; Based on the rotational deviation threshold and rotational correction factor associated with the magnetic resonance examination, the rotational weight is determined. Based on the movement weights and rotation weights, the position deviation and attitude deviation are processed to obtain the deviation score; wherein, the position deviation includes the deviation between the predicted position in the prediction coil pose and the heart position in the current heart pose; the attitude deviation includes the deviation between the predicted attitude in the prediction coil pose and the heart attitude in the current heart pose.

4. The method according to claim 2, characterized in that, Updating the inertia weights of the improved particle swarm optimization algorithm includes: Determine the average distance between parameters in the current population; The inertia weights of the improved particle swarm algorithm are updated based on the average distance, minimum distance threshold, and maximum distance threshold.

5. The method according to claim 2, characterized in that, Determining the control command based on the deviation score includes: If the deviation score is greater than or equal to the score threshold, the adjustment parameter corresponding to the deviation score in the current population will be determined as the control parameter in the control command; The method further includes: If the deviation score in the score set is less than the score threshold, the target parameter is updated based on the score set to obtain the next population set; wherein, the target parameter includes the set of parameters in the current population whose deviation score is less than the score threshold; the score set includes the set of deviation scores corresponding to the parameters in the current population; The improved particle swarm optimization algorithm is used to perform iterative optimization on the current coil pose based on the next swarm set to obtain the control command.

6. An automatic positioning system for a radiofrequency coil in cardiac magnetic resonance imaging (MRI) examination, characterized in that, include: The acquisition module is used to acquire the current heart pose and the current coil pose of the radio frequency coil during a magnetic resonance imaging examination of the heart. A determination module is used to determine the current population based on the current heart pose and the current coil pose; and to determine control commands based on the current population and the current coil pose using the improved particle swarm optimization algorithm; wherein, the current population includes a set of parameters for adjusting the position and / or orientation of the radio frequency coil; and the current population is associated with the improved particle swarm optimization algorithm. A positioning module is used to position the radio frequency coil based on the control command, so as to adjust the relative positional relationship between the radio frequency coil and the heart.

7. The system according to claim 6, characterized in that, The determining module is used to update the inertia weights of the improved particle swarm optimization algorithm; select parameters in the current population based on the updated inertia weights to obtain parameters to be evaluated; predict the predicted coil pose of the radio frequency coil based on the parameters to be evaluated; determine the deviation score between the predicted coil pose and the current heart pose; and determine the control command based on the deviation score.

8. The system according to claim 7, characterized in that, The determining module is used to determine the motion weight based on the motion deviation threshold and translation correction factor associated with the magnetic resonance examination; and to determine the rotation weight based on the rotation deviation threshold and rotation correction factor associated with the magnetic resonance examination. Based on the movement weights and rotation weights, the position deviation and attitude deviation are processed to obtain the deviation score; wherein, the position deviation includes the deviation between the predicted position in the prediction coil pose and the heart position in the current heart pose; the attitude deviation includes the deviation between the predicted attitude in the prediction coil pose and the heart attitude in the current heart pose.

9. The system according to claim 7, characterized in that, The determining module is used to determine the average distance between parameters in the current population; and to update the inertia weights of the improved particle swarm optimization algorithm based on the average distance, the minimum distance threshold, and the maximum distance threshold.

10. The system according to claim 7, characterized in that, The determining module is used to determine the adjustment parameter corresponding to the deviation score in the current population as the control parameter in the control command if the deviation score is greater than or equal to the score threshold. The determining module is used to update the target parameters based on the score set if the deviation score in the score set is less than the score threshold, thereby obtaining the next population set; wherein, the target parameters include the set of parameters in the current population whose deviation scores are less than the score threshold; and the score set includes the set of deviation scores corresponding to the parameters in the current population. The determining module is used to perform iterative optimization processing on the current coil pose based on the next swarm set using the improved particle swarm algorithm to obtain the control command.

Images